Efficient Multiplayer Battle Game Optimizer for Adversarial Robust Neural Architecture Search

• URL: http://arxiv.org/abs/2403.10100v1
• Date: Fri, 15 Mar 2024 08:45:32 GMT
• Title: Efficient Multiplayer Battle Game Optimizer for Adversarial Robust Neural Architecture Search
• Authors: Rui Zhong, Yuefeng Xu, Chao Zhang, Jun Yu,
• Abstract summary: This paper introduces a novel metaheuristic algorithm, known as the efficient multiplayer battle game (EMBGO) The motivation behind this research stems from the need to rectify identified shortcomings in the original MBGO. EMBGO mitigates these limitations by integrating the movement and battle phases to simplify the original optimization framework and improve search efficiency.
• Score: 14.109964882720249
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces a novel metaheuristic algorithm, known as the efficient multiplayer battle game optimizer (EMBGO), specifically designed for addressing complex numerical optimization tasks. The motivation behind this research stems from the need to rectify identified shortcomings in the original MBGO, particularly in search operators during the movement phase, as revealed through ablation experiments. EMBGO mitigates these limitations by integrating the movement and battle phases to simplify the original optimization framework and improve search efficiency. Besides, two efficient search operators: differential mutation and L\'evy flight are introduced to increase the diversity of the population. To evaluate the performance of EMBGO comprehensively and fairly, numerical experiments are conducted on benchmark functions such as CEC2017, CEC2020, and CEC2022, as well as engineering problems. Twelve well-established MA approaches serve as competitor algorithms for comparison. Furthermore, we apply the proposed EMBGO to the complex adversarial robust neural architecture search (ARNAS) tasks and explore its robustness and scalability. The experimental results and statistical analyses confirm the efficiency and effectiveness of EMBGO across various optimization tasks. As a potential optimization technique, EMBGO holds promise for diverse applications in real-world problems and deep learning scenarios. The source code of EMBGO is made available in \url{https://github.com/RuiZhong961230/EMBGO}.

Related papers

• Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System [75.25394449773052]
  Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving. Yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods. We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness.
  arXiv  Detail & Related papers  (2024-10-10T17:00:06Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• The Firefighter Algorithm: A Hybrid Metaheuristic for Optimization Problems [3.2432648012273346]
  The Firefighter Optimization (FFO) algorithm is a new hybrid metaheuristic for optimization problems. To evaluate the performance of FFO, extensive experiments were conducted, wherein the FFO was examined against 13 commonly used optimization algorithms. The results demonstrate that FFO achieves comparative performance and, in some scenarios, outperforms commonly adopted optimization algorithms in terms of the obtained fitness, time taken for exaction, and research space covered per unit of time.
  arXiv  Detail & Related papers  (2024-06-01T18:38:59Z)
• Reinforced In-Context Black-Box Optimization [64.25546325063272]
  RIBBO is a method to reinforce-learn a BBO algorithm from offline data in an end-to-end fashion. RIBBO employs expressive sequence models to learn the optimization histories produced by multiple behavior algorithms and tasks. Central to our method is to augment the optimization histories with textitregret-to-go tokens, which are designed to represent the performance of an algorithm based on cumulative regret over the future part of the histories.
  arXiv  Detail & Related papers  (2024-02-27T11:32:14Z)
• Hybrid ACO-CI Algorithm for Beam Design problems [0.4397520291340694]
  A novel hybrid version of the Ant colony optimization (ACO) method is developed using the sample space reduction technique of the Cohort Intelligence (CI) algorithm. The proposed work could be investigate for real world applications encompassing domains of engineering, and health care problems.
  arXiv  Detail & Related papers  (2023-03-29T04:37:14Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Efficient Non-Parametric Optimizer Search for Diverse Tasks [93.64739408827604]
  We present the first efficient scalable and general framework that can directly search on the tasks of interest. Inspired by the innate tree structure of the underlying math expressions, we re-arrange the spaces into a super-tree. We adopt an adaptation of the Monte Carlo method to tree search, equipped with rejection sampling and equivalent- form detection.
  arXiv  Detail & Related papers  (2022-09-27T17:51:31Z)
• Battle royale optimizer with a new movement strategy [0.0]
  This paper proposes a modified BRO (M-BRO) in order to improve balance between exploration and exploitation. The complexity of this modified algorithm is the same as the original one. The results show that BRO with additional movement operator performs well to solve complex numerical optimization problems.
  arXiv  Detail & Related papers  (2022-01-19T16:36:13Z)
• A Simple Evolutionary Algorithm for Multi-modal Multi-objective Optimization [0.0]
  We introduce a steady-state evolutionary algorithm for solving multi-modal, multi-objective optimization problems (MMOPs) We report its performance on 21 MMOPs from various test suites that are widely used for benchmarking using a low computational budget of 1000 function evaluations.
  arXiv  Detail & Related papers  (2022-01-18T03:31:11Z)
• ZARTS: On Zero-order Optimization for Neural Architecture Search [94.41017048659664]
  Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency. This work turns to zero-order optimization and proposes a novel NAS scheme, called ZARTS, to search without enforcing the above approximation. In particular, results on 12 benchmarks verify the outstanding robustness of ZARTS, where the performance of DARTS collapses due to its known instability issue.
  arXiv  Detail & Related papers  (2021-10-10T09:35:15Z)
• Batch Sequential Adaptive Designs for Global Optimization [5.825138898746968]
  Efficient global optimization (EGO) is one of the most popular SAD methods for expensive black-box optimization problems. For those multiple points EGO methods, the heavy computation and points clustering are the obstacles. In this work, a novel batch SAD method, named "accelerated EGO", is forwarded by using a refined sampling/importance resampling (SIR) method. The efficiency of the proposed SAD is validated by nine classic test functions with dimension from 2 to 12.
  arXiv  Detail & Related papers  (2020-10-21T01:11:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.